2 papers
cs.LG2026
CodeWalk: Generating Coding Benchmarks by Walking a Problem Graph
Jiaxin Fang, Runyuan He, Arnav Gupta +3
High-quality coding problems are expensive to collect. Benchmarks such as SWE-bench rely on substantial human curation, while synthetic alternatives typically rely on costly model…
cs.LG2026
The Geometry of Saturation: Effective Rank Predicts When Labels Stop Helping in Few-Shot Classification
Arnav Gupta
Few-shot label acquisition lacks a label-free signal for when additional labels cease to improve accuracy: existing stopping criteria either require a held-out validation set (viol…